ecp_apps_delete

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without any annotations, the description takes on the full burden. It discloses important side effects: the supervisor process is stopped and the app's files are removed, plus the 'Irreversible' warning. This transparently conveys the destructive nature of the operation. It does not, however, mention any potential cascade effects or failures (e.g., if the app doesn't exist or files are in use), but for the given granularity this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise and front-loaded. The main action ('Delete an app') appears first, followed by a single clause detailing what happens and a clear warning. It's appropriately sized for the operation and adds no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple operation, the description covers the essential behavior (stopping the process and removing files, irreversibility). However, it lacks explicit clarification on the parameters and any expectations about return values or errors. There is no output schema, so a brief note about what the tool returns (e.g., success confirmation) would improve completeness. The description satisfies the core need but leaves minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not explain the 'id' parameter or explicitly state that 'confirm' must be true to proceed. Although the schema shows a required 'confirm' boolean with const:true, the description provides no contextual meaning (e.g., 'You must pass confirm: true to authorize deletion'). The destructive nature of the operation makes this gap more impactful, as the agent may not understand why the confirm field is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete an app'), the specific resource affected ('an app'), and the scope of destruction ('stops its supervisor process (if any) and removes its files'). It directly tells the agent what this tool does without ambiguity, and the sibling list shows distinct operations like ecp_apps_tail_logs and ecp_supervisor_stop_process, so there's no confusion about purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any usage guidance about when to use this tool versus alternative tools, nor does it mention prerequisites or warnings beyond the bare statement 'Irreversible.' There is no reference to related operations such as ecp_apps_deploy or ecp_supervisor_* tools, leaving the agent to infer appropriate usage from the operation name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.